Group Sampling for Scale Invariant Face Detection


For the sake of efficiency, detectors that are based on Deep Learning have a tendency to detect objects of multiple scales within a single input image. Recent works, such as FPN and SSD, generally use feature maps from multiple layers with different spatial resolutions to detect objects at different scales. For instance, high-resolution feature maps are used for detecting small objects. However, our research shows that features extracted from a single layer of the network are sufficient enough to reliably detect objects of any scale. In this paper, we carefully examine the factors affecting detection performance across a wide range of scales. We come to the conclusion that the key is having a balanced set of training samples at various scales, including both positive and negative examples. We propose a method of group sampling in which the anchors are divided into several groups according to the scale, and we make sure that the number of samples that are used for training is the same for all of the groups. The state of the art can be advanced with our method despite the fact that we only use a single layer of FPN for our features. In order to demonstrate that the suggested approach is effective, exhaustive research and testing have been carried out. In addition, we demonstrate that our method is advantageously applicable to other tasks, such as the detection of objects on the COCO dataset, as well as to other detection pipelines, such as YOLOv3, SSD, and R-FCN. When tested on face detection benchmarks such as FDDB and WIDER FACE datasets, our method achieves state-of-the-art results without the use of bells and whistles.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Large Scale Tensor Factorization via Parallel Sketches ABSTRACT: In recent years, tensor factorization methods have seen a rise in their level of popularity. Tensors are appealing for a number of reasons, one of
PROJECT TITLE : Optimal Scale Combination Selection Integrating Three-Way Decision With Hasse Diagram ABSTRACT: In the field of machine learning, the multi-scale decision system, also known as MDS, is a useful tool for describing
PROJECT TITLE : Large-Scale Affine Matrix Rank Minimization With a Novel Nonconvex Regularizer ABSTRACT: The goal of low-rank minimization is to recover a matrix with the lowest possible rank while still satisfying the constraints
PROJECT TITLE : Blockchain Scaling using Rollups A Comprehensive Survey ABSTRACT: In recent years, blockchain systems have experienced significant expansion as a direct result of the enormous potential offered by the technology
PROJECT TITLE : From Pairwise Comparisons and Rating to a Unified Quality Scale ABSTRACT: The purpose of psychometric scaling is to quantify perceptual experiences and comprehend the relationship between an external stimulus,

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry